mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-06-24 13:45:24 -04:00
119228a6db
Add official Gemma 4 12B-it plus QAT-INT4/INT8 catalog entries (with their GGUF sources), QAT quantization support across the quant tables and the prequantized-prefix list, and the missing RTX 3050 / 3050 Ti memory bandwidth so speed estimates stop falling back to the generic cuda value.